Using NEWUOA to drive the autonomous visual modeling of an object by a Humanoid Robot

Torea Foissotte 1, 2 Olivier Stasse 2 Pierre-Brice Wieber 2, 3 Abderrahmane Kheddar 2, 1, *
* Corresponding author
1 IDH - Interactive Digital Humans
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
3 BIPOP - Modelling, Simulation, Control and Optimization of Non-Smooth Dynamical Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : A significant amelioration of our previous work is presented aiming at building autonomously visual models of unknown objects, with a humanoid robot. Previously we introduced a Next-Best-View solution using two stages: (i) an optimization algorithm without derivatives finds a camera pose maximizing the amount of unknown data visible, and (ii) a whole robot posture is generated with a different optimization method where the computed camera pose is set as a constraint on the robot head. The original algorithm is modified in order to improve the robustness while broadening the cases that can be handeld. More specifically, the visibility constraint on the object's land- marks and the unknown quantification is improved while a new constraint is introduced to avoid specific poses.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00567680
Contributor : Pierre-Brice Wieber <>
Submitted on : Monday, February 21, 2011 - 4:17:14 PM
Last modification on : Tuesday, February 12, 2019 - 7:14:02 PM
Document(s) archivé(s) le : Sunday, May 22, 2011 - 2:41:15 AM

File

icia09.pdf
Files produced by the author(s)

Identifiers

Citation

Torea Foissotte, Olivier Stasse, Pierre-Brice Wieber, Abderrahmane Kheddar. Using NEWUOA to drive the autonomous visual modeling of an object by a Humanoid Robot. ICIA: International Conference on Information and Automation, Jun 2009, Zhuhai, China. pp.78-83, ⟨10.1109/ICINFA.2009.5204897⟩. ⟨inria-00567680⟩

Share

Metrics

Record views

628

Files downloads

240